Kelly Criterion & Trading

[alj92]

Hello everyone,

Just curious if anyone uses the Kelly Method in their trading?

If so, have you found it more successful than a flat stake plan?

[LeTiss]

I have my own staking plan which Excel operates perfectly. This has been refined over many years, so I don't use Kelly - I know others do though, as it's been mentioned here on numerous occasions by others

It's good that you are looking at Kelly though, as that shows you are looking to remain in control of your trading bank.

In my experience, this is one of the primary reasons why people fail at trading - their stakes are unreasonable or disproportionate, and this leads to a gambling mindset, as opposed to trading

[convoysur-2]

hi
ive never heard of kelly method,,
any one got a link or explination of it ?
thanks
Marc

[LinusP]

I always use level stakes.

http://www.betfairprotrader.co.uk/2012/ ... erion.html

[burdo77]

Here's some good examples applied to the stock-market


http://www.oldschoolvalue.com/blog/inve ... io-sizing/.

I think Kelly is good if you understand the probability of your trades.....

[burdo77]

Here's a fantastic post at the end of this article

I had this thought too and I like your idea of using confidence levels. Here is another idea:

Instead of estimating the probability based on stock value, why not look at your own track record as an investor?

As a simple example, if 50% of your investments have historically made money and 50% have lost money, the probability involved in your next purchase making money is 0.5. You could make it more sophisticated by calculating the historical probability of your investments hitting their target levels.

[alj92]

I have my own staking plan which Excel operates perfectly. This has been refined over many years, so I don't use Kelly - I know others do though, as it's been mentioned here on numerous occasions by others

It's good that you are looking at Kelly though, as that shows you are looking to remain in control of your trading bank.

In my experience, this is one of the primary reasons why people fail at trading - their stakes are unreasonable or disproportionate, and this leads to a gambling mindset, as opposed to trading

I have been prematch betting for years now, and have used the Kelly Method to exploit the edge in my numbers compared to the bookmakers. I have been testing my numbers in trading for the past couple of months, and during that time reading plenty of articles/watching videos. I lost count of the number I closed out simply because the user was trading a match in a league he had no knowledge of, because his "strategy fit the match". I believe specializing in a league, and maximizing your edge will be far more successful than having a high volume of trades. Money management is built into the Kelly Method, but of course, the key is identifying your edge, and estimating it accurately. My problem now is trying to find a use for my estimation of implied win probability in a proper trading strategy.

[Euler]

Have you looked at optimal f?

http://www.dummies.com/how-to/content/t ... style.html

[Wyndon]

There is an excellent readable book on the subject, which intersperses the theory with some great stories of real-life attempts to beat the stock market/casinos/sports betting etc., sometimes involving shady characters as well as maths whiz kids. "Fortune's Formula" by William Poundstone. As mentioned somewhere above, the difficulty is in quantifying your edge. I'm pretty sure that calculating an overall average edge rather than attempting to identify individual edges does not lead to such spectacular results.